route_verdict

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations (readOnlyHint=true), the description adds critical behavioral context: it is a paid operation (credit cost), has rate limits (10/day for preview), requires authentication for full tier (TENSORFEED_TOKEN), and describes output contents (reasoning, runners-up, signed receipt). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (three sentences) and front-loaded with the tool's purpose. It efficiently covers multiple aspects (purpose, tiers, costs, auth) without unnecessary verbosity. Slightly dense but acceptable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with 8 parameters and no output schema, the description provides substantial context: data sources, tier behavior, constraints, authentication, and output summary. Missing details on exact output format, but overall sufficient for an agent to decide and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds marginal value beyond the schema, such as explaining tier differences and that task or model must be provided. The schema already adequately documents all parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns a signed model-routing decision, specifying it fuses multiple data sources (pricing, benchmarks, latency, etc.) to recommend the single best model for a task or named model. It distinguishes between free preview and paid full tiers, avoiding tautology and providing specific verb+resource.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use (for model routing decisions) and provides context on tier costs, rate limits, and authentication needs. However, it does not explicitly mention when not to use or list alternative sibling tools (e.g., failover_verdict, benchmark_series), leaving some ambiguity for the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.